/R2P2: A ReparameteRized Pushforward Policy for Diverse, Precise Generative Path Forecasting

R2P2: A ReparameteRized Pushforward Policy for Diverse, Precise Generative Path Forecasting

Nick Rhinehart, Paul Vernaza and Kris Kitani
Conference Paper, European Conference on Computer Vision (ECCV 2018), Part of the Lecture Notes in Computer Science book series (LNCS, volume 11217), pp. 794 - 811, October, 2018

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author’s copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract

We propose a method to forecast a vehicle’s ego-motion as a distribution over spatiotemporal paths, conditioned on features (e.g., from LIDAR and images) embedded in an overhead map. The method learns a policy inducing a distribution over simulated trajectories that is both “diverse” (produces most paths likely under the data) and “precise” (mostly produces paths likely under the data). This balance is achieved through minimization of a symmetrized cross-entropy between the distribution and demonstration data. By viewing the simulated-outcome distribution as the pushforward of a simple distribution under a simulation operator, we obtain expressions for the cross-entropy metrics that can be efficiently evaluated and differentiated, enabling stochastic-gradient optimization. We propose concrete policy architectures for this model, discuss our evaluation metrics relative to previously-used metrics, and demonstrate the superiority of our method relative to state-of-the-art methods in both the Kitti dataset and a similar but novel and larger real-world dataset explicitly designed for the vehicle forecasting domain.

BibTeX Reference
@conference{Rhinehart-2018-109777,
author = {Nick Rhinehart and Paul Vernaza and Kris Kitani},
title = {R2P2: A ReparameteRized Pushforward Policy for Diverse, Precise Generative Path Forecasting},
booktitle = {European Conference on Computer Vision (ECCV 2018), Part of the Lecture Notes in Computer Science book series (LNCS, volume 11217)},
year = {2018},
month = {October},
pages = {794 - 811},
}
2018-11-06T16:29:37+00:00